Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    statements introducing significance or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     op
    -0.59
    principalTable
    -0.58
     виправивши
    -0.57
    %");
    -0.56
     beginnetje
    -0.55
     ?>>
    -0.55
    '){
    -0.55
    __()
    -0.53
    balleur
    -0.53
    ':
    -0.53
    POSITIVE LOGITS
    That
    2.09
     That
    1.94
    Thats
    1.23
     Thats
    1.21
    THAT
    1.17
    Which
    1.07
     THAT
    1.06
     Which
    0.90
    thats
    0.85
     Jefus
    0.81
    Act Density 0.051%

    No Known Activations